Computational Privacy Group - Imperial College London

Today people leave digital breadcrumbs wherever they go and whatever they do online and offline. This data dramatically increases our capacity to understand and affect the behavior of individuals and collectives, has been key to recent advances in AI, but also raises fundamentally new privacy and fairness questions. The Computational Privacy Group aims to provide leadership, in the UK and beyond, in the safe, anonymous, and ethical use of large-scale behavioral datasets coming from the Internet of Things (IoT) devices, mobile phones, credit cards, browsers, etc.

Our projects have already demonstrated the limits of data anonymization (or de-identification) in effectively protecting the privacy of individuals in Big Data, the risk of inference in behavioral datasets coming from mobile phone, and developed solutions to allow individuals and companies to share data safely. While technical in nature, our work has had significant public policy implication for instance in reports of United Nations, FTC, and the European Commission as well as in briefs to the U.S. Supreme Court.

Research Areas

Identification Learning

We develop statistical and machine learning techniques to uniquely identify individuals in large-scale behavioral datasets. These techniques show the limits of pseudonymization and anonymization in protecting people's privacy.

Safe Data Sharing

We build privacy-preserving and conscientious techniques to collect and use data while respecting people's privacy. For instance, we're building with MIT the OPAL (Open Algorithms) platform to safely share location data and openPDS to give individuals control over their data.

Societal impact of AI

Modern privacy is not only about controlling the information but also the ability to control how this information is used e.g. for insurance pricing or ad-targeting. We study fairness in algorithmic-decision making and, more generally, the impact of AI on society.

News and Events

CPG at CNIL Privacy Research Day

Jul 14, 2023

The CPG attended the CNIL Privacy Research Day in Paris in June 2023. Ana-Maria Crețu presented her paper on automated privacy attacks (Querysnout), Shubham Jain presented both papers on perceptual hashing and Florent Guépin presented his paper on correlation inference attacks.

CPG at ACM CCS 2022

Nov 10, 2022

Ana-Maria Cretu and CPG alumnus Florimond Houssiau (currently a postdoc at The Alan Turing Institute) presented their paper “QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systems” at the ACM CCS 2022 conference in Los Angeles.

New paper “Expanding the attack surface: Robust profiling attacks threaten the privacy of sparse behavioral data” published in Science Advances

Aug 19, 2022

In a new paper published in Science Advances, Arnaud J. Tournier and Yves-Alexandre de Montjoye propose an entropy-based profiling attack for location data which shows that much more auxiliary information than previously believed is available to re-identify individuals in …

More News

Tweets by CPG

Selected publications

Meeus, M., Jain, S., and de Montjoye Y. A. Concerns about using a digital mask to safeguard patient privacy. Matters Arising in Nature Medicine, July 2023 (2023).
Jain, S., Cretu, A.-M., Cully, A. and de Montjoye Y. A. Deep perceptual hashing algorithms with hidden dual purpose: when client-side scanning does facial recognition. 2023 IEEE Symposium on Security and Privacy (SP) (2023).
Selected Press: Imperial College London News
Rocher, L., Tournier, A. J., & de Montjoye, Y. A. Adversarial competition and collusion in algorithmic markets. Nature Machine Intelligence (2023).
Selected Press: POLITICO Pro Fair Play, POLITICO Pro Morning Tech
Houssiau, F., Liénart, T., Hendrickx, J. and de Montjoye Y. A. Web privacy: a Formal Adversarial Model for Query Obfuscation. IEEE Transactions on Information Forensics and Security (2023).
Houssiau, F., Sapieżyński, P., Radaelli, L., Shmueli, E. and de Montjoye Y. A. Detrimental network effects in privacy: A graph-theoretic model for node-based intrusions. Patterns, 4(1) (2023).
Houssiau, F., Schellekens, V., Chatalic, A., Annamraju, S. K. and de Montjoye Y. A. M2M: A General Method to Perform Various Data Analysis Tasks from a Differentially Private Sketch. The 18th International Workshop on Security and Trust Management (2022).
Cretu, A.-M.*, Houssiau, F.*, Cully, A., and de Montjoye Y. A. QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systems. In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security (CCS '22). Association for Computing Machinery, New York, NY, USA, 623–637. (2022).
Selected Press: Imperial College London
Tournier, A. J., & de Montjoye, Y. A. Expanding the attack surface: Robust profiling attacks threaten the privacy of sparse behavioral data. Science Advances (2022).
Gadotti A., Houssiau F., Annamalai M.S.M.S., & de Montjoye, Y. A. Pool Inference Attacks on Local Differential Privacy: Quantifying the Privacy Guarantees of Apple's Count Mean Sketch in Practice. 31st USENIX Security Symposium (2022).
Jain, S.*, Cretu, A.-M.*, and de Montjoye Y. A. Adversarial Detection Avoidance Attacks: Evaluating the robustness of perceptual hashing-based client-side scanning. 31st USENIX Security Symposium (2022).
Selected Press: Imperial College London News
Cretu, A.-M., Monti, F., Marrone, S., Dong, X., Bronstein, M. and de Montjoye Y. A. Interaction data are identifiable even across long periods of time. Nature Communications (13), 313 (2022).
Selected Press: Science News, RFI
Houssiau, F., Rocher, L. and de Montjoye Y. A. On the difficulty of achieving Differential Privacy in practice: user-level guarantees in aggregate location data. Nature Communications, 2022 (2022).
Gadotti A., Houssiau F., Rocher L., Livshits B., de Montjoye Y. A. When the signal is in the noise: Exploiting Diffix's Sticky Noise. 28th USENIX Security Symposium (2019).
Selected Press: TechCrunch, Wall Street Journal
Rocher, L., Hendrickx, J. M., & de Montjoye, Y. A. Estimating the success of re-identifications in incomplete datasets using generative models. Nature communications, 10 (1), 3069 (2019).
Selected Press: New York Times, Guardian, CNBC, The Telegraph, TechCrunch, Technology Review, New Scientist, Gizmodo, Scientific American, RT, Forbes, El Pais (ES), Sueddeutsche Zeitung (DE), Le Soir (FR), La Libre (FR), L'Echo (FR), De Morgen (NL)
de Montjoye Y. A., Radaelli L., Singh V. K., Pentland A., Unique in the shopping mall: On the reidentifiability of credit card metadata. Science 347 (6221), 536-539. DOI:10.1126/science.1256297 (2015).
Selected Press: New York Times, Wall Street Journal (1, 2), BBC, Harvard Business Review, Nature, Technology Review, Le Monde (FR), Die Zeit (DE), Die Spiegel (DE), El Pais (ES), The Hill, Les Echos (FR), Scientific American, New Scientist, Five Thirty Eight
de Montjoye Y. A., Shmueli E., Wang S., Pentland A., openPDS: Protecting the Privacy of Metadata through SafeAnswers. PLoS One, 10.1371 (2014).
Selected Press: BBC, New-York Times, Wall Street Journal, Technology Review, World Economic Forum, Real Time with Bill Maher (HBO), Le Monde (FR), MIT News, Wired (UK), New Scientist, Baratunde for Fast Company, GigaOM, Scientific American (1, 2)
de Montjoye Y.-A.*, Quoidbach J.*, Robic F.*, Pentland A., Predicting people personality using novel mobile phone-based metrics. International Conference on Social Computing, Behavioral-Cultural Modeling, & Prediction, Washington, USA (2013).
Selected Press: Le Monde (FR), RT, Boston Globe, Mediapart (FR), Radio Canada (FR)
de Montjoye Y.-A., Hidalgo C. A., Verleysen M., Blondel V. D., Unique in the Crowd: The privacy bounds of human mobility. Nature srep. 3, 1376; DOI:10.1038/srep01376 (2013).
Selected Press: BBC, CNN, Wall Street Journal, New-York Times ( 1, 2), Le Monde (FR) (1, 2), Guardian (UK), Technology Review, Nature, Wired (US, UK, JP), Bruce Schneier, Der Spiegel (DE), Die Welt (DE) (1, 2), Boing Boing, Fast Company, PopSci, GigaOM, TechDirt

The full list of our papers is available on Google Scholar.

Our Team

Yves-Alexandre de Montjoye

Group leader

Yves-Alexandre is an Associate Professor at Imperial College London. He received his PhD from MIT before joining Harvard IQSS for his postdoc. He currently is a Special Adviser on AI and Data Protection to EC Justice Commissioner Reynders and a Parliament-appointed expert to the Belgian Data Protection Agency (APD-GBA).

Ana-Maria Cretu

PhD student

Originally from Romania, Ana-Maria has a background in mathematics and computer science. Her research focuses on new machine learning-based privacy and security attacks in large-scale behavioral datasets, machine learning models, query-based and client-side scanning systems.

Vince Guan

PhD student

Originally from Canada, Vince studied mathematics at the University of British Columbia for his Bachelor’s degree (BA with Major in Mathematics with Minor in Philosophy) and Master’s degree (MSc in Mathematics). His research interests include privacy attacks against aggregate location data, synthetic data generation, AI fairness, and interpretable machine learning.

Florent Guepin

PhD student

Florent received his BSc and MSc in theoretical computing from ENS Lyon. He also holds a BSc in pure maths from University Lyon 1 an engineering degree from Centrale Lyon. His research interests include privacy attacks against machine learning systems and generative systems such as GANs.

Shubham Jain

PhD student

Originally from India, Shubham received a BTech in computer science and engineering from IIT Bombay. His research interests include fairness in machine learning systems, scalable privacy-preserving systems, and network security.

Yifeng Mao

PhD student

Originally from China, Yifeng obtained his bachelor degree from Tsinghua University in Automation. Then, he finished his master degree and spent one year working as a full-time research assistant in the United States. His research interests include privacy-preserving machine learning, synthetic data generation protecting personal anonymity, and attack methods against census datasets and generic ML models.

Matthieu Meeus

PhD student

Originally from Belgium, Matthieu obtained his BSc from KU Leuven in Mechanical Engineering. Afterwards he spent four years in the US, pursuing two years of graduate study in Energy and Computational Science and two years of working as data scientist in a consulting company. His research interests include privacy attacks against computer vision and language models and bias and fairness in machine learning.

Bozhidar Stevanoski

PhD student

Bozhidar has obtained his MSc in Data Science at the University of Ljubljana and his BSc in Computer Science at the Ss. Cyril and Methodius University in Skopje. His research interests include machine learning and privacy attacks against query-based systems.

Andrea Gadotti

Honorary Research Associate

Andrea received a BSc in math and a MSc in mathematical logic from the University of Turin. His research interests include differential privacy, privacy attacks against systems processing personal data, and the design of privacy-preserving mechanisms.

Luc Rocher

Honorary Research Associate

Luc is a postdoctoral researcher studying the limits of privacy in the modern age, and received a PhD in Applied mathematics from UCLouvain. Luc's work has challenged the technical and legal adequacy of current de-identification techniques to anonymise data.

Amandeep Bahia

Research Group Administrator

Amandeep supports the day-to-day running of the Data Science Institute in terms of finance, HR and general office management.

CPG Alumni →

Contact

Email:X@Y where X=demontjoye, Y=imperial.ac.uk.
Administrator (if urgent): Amandeep Bahia, +44 20 7594 8612

We are located at the Data Science Institute in the William Penney Laboratory. The best entry point is via Exhibition road, through the Business school (see map below). From there, just take the stairs towards the outdoor court. Enter the outdoor corridor after the court and the institute will be on your right (please press the Data Science intercom button for access).

Please address mails to:
Department of Computing
Imperial College London
180 Queens Gate
London SW7 2AZ

Somewhere